Cohere Parse scored 79.2 on ParseBench, outperforming Mistral OCR 4 (74.5), Databricks AI Parse (72.4), and LlamaParse (78.3). The vision language model converts multimodal enterprise documents into structured Markdown, handling tables, forms, and images across nine languages. Priced at $1.50 per 1,000 pages via the Cohere API, it is also available in Model Vault and as part of Compass alongside Embed and Rerank.
No score is assigned. Sources and their independence are shown in the citation chain below.